Create app.py

app.py

@@ -0,0 +1,122 @@
+import os
+os.environ["TOKENIZERS_PARALLELISM"] = "false"
+
+import streamlit as st
+from st_aggrid import AgGrid
+import pandas as pd 
+from transformers import pipeline, T5ForConditionalGeneration, T5Tokenizer
+
+st.set_page_config(layout="wide")
+
+style = '''
+    <style>
+        body {background-color: #F5F5F5; color: #000000;}
+        header {visibility: hidden;}
+        div.block-container {padding-top:4rem;}
+        section[data-testid="stSidebar"] div:first-child {
+        padding-top: 0;
+    }
+     .font {                                          
+    text-align:center;
+    font-family:sans-serif;font-size: 1.25rem;}
+    </style>
+'''
+st.markdown(style, unsafe_allow_html=True)
+
+st.markdown('<p style="font-family:sans-serif;font-size: 1.9rem;"> HertogAI Q&A table V1 using TAPAS and Text Generated</p>', unsafe_allow_html=True)
+st.markdown("<p style='font-family:sans-serif;font-size: 0.9rem;'>Pre-trained TAPAS model runs on max 64 rows and 32 columns data. Make sure the file data doesn't exceed these dimensions.</p>", unsafe_allow_html=True)
+
+# Initialize TAPAS and Hugging Face Model (T5 for NLP generation)
+tqa = pipeline(task="table-question-answering", 
+              model="google/tapas-large-finetuned-wtq",
+              device="cpu")
+
+model_name = "t5-small"  # You can use a larger model or GPT as needed
+tokenizer = T5Tokenizer.from_pretrained(model_name)
+model = T5ForConditionalGeneration.from_pretrained(model_name)
+
+# Function to generate natural language from TAPAS output
+def generate_nlp_from_tapas(tapas_output, df):
+    """
+    Use Hugging Face's T5 model to generate natural language text from TAPAS output.
+    """
+    try:
+        # Construct prompt using TAPAS output
+        answer = tapas_output['answer']
+        coordinates = tapas_output['coordinates']
+        answer_data = [df.iloc[row, col] for row, col in coordinates]
+
+        # Format the prompt for NLP model
+        prompt = f"Answer: {answer}. Data Location: Rows {coordinates}, Values: {answer_data}. Please summarize this information in a natural language sentence."
+
+        # Tokenize input and generate response
+        inputs = tokenizer.encode(prompt, return_tensors="pt", truncation=True, max_length=512)
+        outputs = model.generate(inputs, max_length=100, num_beams=5, early_stopping=True)
+
+        # Decode and return the generated response
+        response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        return response
+    except Exception as e:
+        return f"Error generating response: {str(e)}"
+
+
+file_name = st.sidebar.file_uploader("Upload file:", type=['csv', 'xlsx'])
+
+if file_name is None:
+    st.markdown('<p class="font">Please upload an excel or csv file </p>', unsafe_allow_html=True)
+else:
+    try:
+        # Check file type and handle reading accordingly
+        if file_name.name.endswith('.csv'):
+            df = pd.read_csv(file_name, sep=';', encoding='ISO-8859-1')  # Adjust encoding if needed
+        elif file_name.name.endswith('.xlsx'):
+            df = pd.read_excel(file_name, engine='openpyxl')  # Use openpyxl to read .xlsx files
+        else:
+            st.error("Unsupported file type")
+            df = None
+
+        # Continue with further processing if df is loaded
+        if df is not None:
+            numeric_columns = df.select_dtypes(include=['object']).columns
+            for col in numeric_columns:
+                df[col] = pd.to_numeric(df[col], errors='ignore')
+
+            st.write("Original Data:")
+            st.write(df)
+
+            # Create a copy for numerical operations
+            df_numeric = df.copy()
+            df = df.astype(str)
+
+            grid_response = AgGrid(
+                df.head(5),
+                columns_auto_size_mode='FIT_CONTENTS',
+                editable=True, 
+                height=300, 
+                width='100%',
+            )
+            
+    except Exception as e:
+        st.error(f"Error reading file: {str(e)}")
+
+    question = st.text_input('Type your question')
+    
+    with st.spinner():
+        if(st.button('Answer')):
+            try:
+                # Get the raw answer from TAPAS
+                raw_answer = tqa(table=df, query=question, truncation=True)
+                
+                st.markdown("<p style='font-family:sans-serif;font-size: 0.9rem;'> Raw Result: </p>", unsafe_allow_html=True)
+                st.success(raw_answer)
+                
+                # Use Hugging Face's T5 model to generate NLP text from TAPAS output
+                final_answer = generate_nlp_from_tapas(raw_answer, df)
+
+                # Display the generated answer in a simple format
+                st.markdown("<p style='font-family:sans-serif;font-size: 0.9rem;'> Generated Answer: </p>", unsafe_allow_html=True)
+                st.success(final_answer)
+
+            except Exception as e:
+                st.warning(f"Error: {str(e)} - Please retype your question and ensure it is correctly formatted.")
+